[PATCH v2] x86: Use assembly instruction mnemonics instead of .byte streams in arch_hweight.h

From: Uros Bizjak
Date: Sun Oct 14 2018 - 16:24:25 EST


Recently the minimum required version of binutils was changed to 2.20,
which supports popcnt instruction mnemonics. The patch removes
corresponding #defines that implement popcnt instructions using target-dependant
.byte streams and uses unified instruction mnemonics instead.

Tested by building x86_64 and i386 version of the kernel and comparing
objdump dumps of the pathced and unpatched vmlinux.o. They were the same.

v2: Update commit message to emphasize removal of #defines.

Signed-off-by: Uros Bizjak <ubizjak@xxxxxxxxx>
---
arch/x86/include/asm/arch_hweight.h | 12 ++++--------
1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 34a10b2d5b73..d668e411bd32 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -5,15 +5,9 @@
#include <asm/cpufeatures.h>

#ifdef CONFIG_64BIT
-/* popcnt %edi, %eax */
-#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7"
-/* popcnt %rdi, %rax */
-#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
#define REG_IN "D"
#define REG_OUT "a"
#else
-/* popcnt %eax, %eax */
-#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0"
#define REG_IN "a"
#define REG_OUT "a"
#endif
@@ -24,7 +18,8 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w)
{
unsigned int res;

- asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
+ asm (ALTERNATIVE("call __sw_hweight32",
+ "popcntl %1, %0", X86_FEATURE_POPCNT)
: "="REG_OUT (res)
: REG_IN (w));

@@ -52,7 +47,8 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
{
unsigned long res;

- asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
+ asm (ALTERNATIVE("call __sw_hweight64",
+ "popcntq %1, %0", X86_FEATURE_POPCNT)
: "="REG_OUT (res)
: REG_IN (w));

--
2.17.2